prospecting

Warn

Audited by Snyk on Jul 27, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.75). SKILL.md’s required prospecting flow for candidate qualification uses runtime lookups to public sources (e.g., “Source 2–3× more candidates… LinkedIn, Yelp, business websites, forums/GitHub issues/job posts” and “Evidence… a source URL or two”), which can include outsider-authored free-text from those pages/threads that the agent reads and summarizes into the LLM context.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 27, 2026, 12:30 AM
Issues
1
Security Audit — snyk — prospecting